library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.5.1 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.1
## ✔ purrr 1.0.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(completejourney)
## Welcome to the completejourney package! Learn more about these data
## sets at http://bit.ly/completejourney.
library(dplyr)
library(ggplot2)
coupon_redemptions %>%
inner_join(coupons, by = "coupon_upc") %>%
inner_join(products, by = "product_id") %>%
inner_join(demographics, by = "household_id") %>%
group_by(household_id, coupon_upc) %>%
summarise(total_coupons = n()) %>%
group_by(household_id) %>%
summarise(total_coupons_per_household = sum(total_coupons)) %>%
arrange(desc(total_coupons_per_household)) %>%
top_n(10, total_coupons_per_household) %>%
ggplot(aes(x = reorder(as.factor(household_id), -total_coupons_per_household),
y = total_coupons_per_household, group = 1)) +
geom_line(color = "green", size = 1) +
geom_point(color = "black", size = 3) +
scale_x_discrete("Household Identifier") +
scale_y_continuous("Total Coupons Redeemed Across Products") +
ggtitle("Top 10 Households by Coupon Usage Across Products",
subtitle = "Line chart illustrating total coupons redeemed for each household.")
## Warning in inner_join(., coupons, by = "coupon_upc"): Detected an unexpected many-to-many relationship between `x` and `y`.
## ℹ Row 1 of `x` matches multiple rows in `y`.
## ℹ Row 91127 of `y` matches multiple rows in `x`.
## ℹ If a many-to-many relationship is expected, set `relationship =
## "many-to-many"` to silence this warning.
## `summarise()` has grouped output by 'household_id'. You can override using the
## `.groups` argument.
## Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
## ℹ Please use `linewidth` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
library(ggplot2)
library(dplyr)
library(completejourney)
library(tidyverse)
library(lubridate)
transactions_sample %>%
inner_join(products) %>%
inner_join(demographics) %>%
filter(product_category == "SUSHI") %>%
group_by(income) %>%
summarize(total_sushi_purchases = sum(quantity, na.rm = TRUE)) %>%
ggplot(aes(x = income, y = total_sushi_purchases, fill = total_sushi_purchases)) +
geom_col() +
labs(
title = "Total Sushi Purchases by Income Level",
subtitle = "Hypothesis: Customers with higher incomes (150k+) are expected to \n purchase more sushi due to its premium price.",
x = "Annual Income Levels ($)",
y = "Number of Sushi Purchases") +
theme(plot.title = element_text(hjust = 0.5, face = "bold")) +
theme(plot.subtitle = element_text(hjust = 0.5, face = "italic"))
## Joining with `by = join_by(product_id)`
## Joining with `by = join_by(household_id)`
library(tidyverse)
library(completejourney)
library(dplyr)
library(ggplot2)
products %>%
filter(str_detect(product_category, regex("(SODA)|(JUICE)|(WATER)", ignore_case = TRUE))) %>%
inner_join(transactions_sample, by = "product_id") %>%
inner_join(demographics, by = "household_id") %>%
group_by(income, age) %>%
summarise(total_sales = sum(sales_value, na.rm = TRUE)) %>%
mutate(age = fct_na_value_to_level(age, level = "Unknown")) %>%
ggplot(aes(x = age, y = total_sales)) +
geom_col(fill = "green") +
facet_wrap(~ income) +
scale_x_discrete("Age Category") +
scale_y_continuous("Total Beverage Sales", labels = scales::dollar) +
ggtitle("Purchases Beverages by Age Group and Income?",
subtitle = "The age group from 35-44 with an income of $50-74K buys the most beverages.")
## `summarise()` has grouped output by 'income'. You can override using the
## `.groups` argument.
